{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5XDM46GRTBAW5R3MH4QALND7JP","short_pith_number":"pith:5XDM46GR","canonical_record":{"source":{"id":"2502.14376","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T09:06:44Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5fe03411cf3f969f3c966377ba408e725793b8a8848440528a191e0c6a01209c","abstract_canon_sha256":"5059d11e07f4cea622679263f1a7418257db491a968cdb210980e60a7906ae27"},"schema_version":"1.0"},"canonical_sha256":"edc6ce78d198416ec76c3f2005b47f4bcf3c0b4e032a85204342e1642046285c","source":{"kind":"arxiv","id":"2502.14376","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14376","created_at":"2026-07-05T11:14:27Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14376v2","created_at":"2026-07-05T11:14:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14376","created_at":"2026-07-05T11:14:27Z"},{"alias_kind":"pith_short_12","alias_value":"5XDM46GRTBAW","created_at":"2026-07-05T11:14:27Z"},{"alias_kind":"pith_short_16","alias_value":"5XDM46GRTBAW5R3M","created_at":"2026-07-05T11:14:27Z"},{"alias_kind":"pith_short_8","alias_value":"5XDM46GR","created_at":"2026-07-05T11:14:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5XDM46GRTBAW5R3MH4QALND7JP","target":"record","payload":{"canonical_record":{"source":{"id":"2502.14376","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T09:06:44Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5fe03411cf3f969f3c966377ba408e725793b8a8848440528a191e0c6a01209c","abstract_canon_sha256":"5059d11e07f4cea622679263f1a7418257db491a968cdb210980e60a7906ae27"},"schema_version":"1.0"},"canonical_sha256":"edc6ce78d198416ec76c3f2005b47f4bcf3c0b4e032a85204342e1642046285c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:27.570830Z","signature_b64":"nOtDc8v99rTgMqdiVqC//2EoDm1ZDM16154SULLrDzafb7c/EgUq3iAKby8HusSAKGpZIS+DqKcJbWowA8gSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"edc6ce78d198416ec76c3f2005b47f4bcf3c0b4e032a85204342e1642046285c","last_reissued_at":"2026-07-05T11:14:27.570377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:27.570377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.14376","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:14:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s84skcY8j34By8zi+tROr8SGFjrlSYQ4/V9YADvsTuXlEZu6Gk+64t7pNBXzCVcy+99Y/c7htjQu/DhpnfweDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:48:04.066905Z"},"content_sha256":"50ea0088c2c39867ee31c82a8ed16fb8ca45f23908c9102b2ffd9c94ce6e6ef7","schema_version":"1.0","event_id":"sha256:50ea0088c2c39867ee31c82a8ed16fb8ca45f23908c9102b2ffd9c94ce6e6ef7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5XDM46GRTBAW5R3MH4QALND7JP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Similarity Paradigm Through Textual Regularization Without Forgetting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Fangming Cui, Jan Fong, Jun Yu, Rongfei Zeng, Xinmei Tian","submitted_at":"2025-02-20T09:06:44Z","abstract_excerpt":"Prompt learning has emerged as a promising method for adapting pre-trained visual-language models (VLMs) to a range of downstream tasks. While optimizing the context can be effective for improving performance on specific tasks, it can often lead to poor generalization performance on unseen classes or datasets sampled from different distributions. It may be attributed to the fact that textual prompts tend to overfit downstream data distributions, leading to the forgetting of generalized knowledge derived from hand-crafted prompts. In this paper, we propose a novel method called Similarity Parad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14376","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.14376/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:14:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LWkbl3sH4Vf8DbdRTJUfNAjzSBCTr3KcGtPXu4exnn0EQqZp4xIZmRk/qUaLBzyr7XBdIhk68yHNab4GWM4RCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T08:48:04.067551Z"},"content_sha256":"a31c79fb46ed1935cca5ad792742973b21bdc6276d498748232223276db298b8","schema_version":"1.0","event_id":"sha256:a31c79fb46ed1935cca5ad792742973b21bdc6276d498748232223276db298b8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5XDM46GRTBAW5R3MH4QALND7JP/bundle.json","state_url":"https://pith.science/pith/5XDM46GRTBAW5R3MH4QALND7JP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5XDM46GRTBAW5R3MH4QALND7JP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T08:48:04Z","links":{"resolver":"https://pith.science/pith/5XDM46GRTBAW5R3MH4QALND7JP","bundle":"https://pith.science/pith/5XDM46GRTBAW5R3MH4QALND7JP/bundle.json","state":"https://pith.science/pith/5XDM46GRTBAW5R3MH4QALND7JP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5XDM46GRTBAW5R3MH4QALND7JP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5XDM46GRTBAW5R3MH4QALND7JP","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5059d11e07f4cea622679263f1a7418257db491a968cdb210980e60a7906ae27","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T09:06:44Z","title_canon_sha256":"5fe03411cf3f969f3c966377ba408e725793b8a8848440528a191e0c6a01209c"},"schema_version":"1.0","source":{"id":"2502.14376","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.14376","created_at":"2026-07-05T11:14:27Z"},{"alias_kind":"arxiv_version","alias_value":"2502.14376v2","created_at":"2026-07-05T11:14:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14376","created_at":"2026-07-05T11:14:27Z"},{"alias_kind":"pith_short_12","alias_value":"5XDM46GRTBAW","created_at":"2026-07-05T11:14:27Z"},{"alias_kind":"pith_short_16","alias_value":"5XDM46GRTBAW5R3M","created_at":"2026-07-05T11:14:27Z"},{"alias_kind":"pith_short_8","alias_value":"5XDM46GR","created_at":"2026-07-05T11:14:27Z"}],"graph_snapshots":[{"event_id":"sha256:a31c79fb46ed1935cca5ad792742973b21bdc6276d498748232223276db298b8","target":"graph","created_at":"2026-07-05T11:14:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.14376/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prompt learning has emerged as a promising method for adapting pre-trained visual-language models (VLMs) to a range of downstream tasks. While optimizing the context can be effective for improving performance on specific tasks, it can often lead to poor generalization performance on unseen classes or datasets sampled from different distributions. It may be attributed to the fact that textual prompts tend to overfit downstream data distributions, leading to the forgetting of generalized knowledge derived from hand-crafted prompts. In this paper, we propose a novel method called Similarity Parad","authors_text":"Fangming Cui, Jan Fong, Jun Yu, Rongfei Zeng, Xinmei Tian","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T09:06:44Z","title":"A Similarity Paradigm Through Textual Regularization Without Forgetting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14376","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:50ea0088c2c39867ee31c82a8ed16fb8ca45f23908c9102b2ffd9c94ce6e6ef7","target":"record","created_at":"2026-07-05T11:14:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5059d11e07f4cea622679263f1a7418257db491a968cdb210980e60a7906ae27","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-20T09:06:44Z","title_canon_sha256":"5fe03411cf3f969f3c966377ba408e725793b8a8848440528a191e0c6a01209c"},"schema_version":"1.0","source":{"id":"2502.14376","kind":"arxiv","version":2}},"canonical_sha256":"edc6ce78d198416ec76c3f2005b47f4bcf3c0b4e032a85204342e1642046285c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"edc6ce78d198416ec76c3f2005b47f4bcf3c0b4e032a85204342e1642046285c","first_computed_at":"2026-07-05T11:14:27.570377Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:27.570377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nOtDc8v99rTgMqdiVqC//2EoDm1ZDM16154SULLrDzafb7c/EgUq3iAKby8HusSAKGpZIS+DqKcJbWowA8gSAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:27.570830Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.14376","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50ea0088c2c39867ee31c82a8ed16fb8ca45f23908c9102b2ffd9c94ce6e6ef7","sha256:a31c79fb46ed1935cca5ad792742973b21bdc6276d498748232223276db298b8"],"state_sha256":"c4feb2c4fae3c9220100a33f9cf13a1459688f5e91a96474489b882dd682cbba"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tqTNDXQFtVP4sYUOSkCogKNXk8C3LuOhGKmw0NWwUuaoHtNvapsSt+5ZDoZC/JuA2JclIEDaLQuwa0gCTU9WAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T08:48:04.073222Z","bundle_sha256":"748bc8c74dfdb075da889453d07e8ee5c371d93af1092a9db5d7852d36264d8a"}}